基于灵敏度分析的稳健可靠性优化设计模型及MATLAB实现

Robust Reliability Optimization Design Model Based on Sensitivity Analysis and Its Achieving With MATLAB

在机械零件的可靠性优化设计中，普遍存在约束的作用，且最优解往往位子可行域的边界上。由于外界环境的变化或人为因素造成设计变量扰动，可能使设计成为不可行。本文提出了一种基于设计变量敏感度的稳键性设计方法，建立了基于灵敏度分析产生附加目标函数的两种稳健可靠性优化设计模型，并用 ＭＡＴＬＡＢ语言的优化工具箱和符号工具箱来实现机械零件的稳健可靠性优化设计，计算实例说明所述模型的可行性与实用性。

Generally, action of constraints exists in reliability optimization design 0f mechanical parts, which always makes the optimal points on the boundary of the feasible region. Small disturbances of design variable are likely to make the design infeasible and useless. A general method for robust design is presented based on sensitivity and two models are established for robust reliability optimization design of mechanical parts based on adjunctive function of sensibility of the objective or the objective and constraint functions of the design parameters. Then it is realized with Optimization Toolbox and Symbolic Foolbox of MATLAB5. 3. Design example show the model is practical and effective.